gen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_modelT_gen_dl_pruned_model

HALCON ScriptCpp++.NETPythonC

Short description

gen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_modelT_gen_dl_pruned_model — Prune a deep learning model.

Signature

gen_dl_pruned_model( dl_model DLModelHandleToPrune, dl_pruning DLPruningHandle, out dl_model DLModelHandlePruned )void GenDlPrunedModel( const HTuple& DLModelHandleToPrune, const HTuple& DLPruningHandle, HTuple* DLModelHandlePruned )static void HOperatorSet.GenDlPrunedModel( HTuple DLModelHandleToPrune, HTuple DLPruningHandle, out HTuple DLModelHandlePruned )def gen_dl_pruned_model( dlmodel_handle_to_prune: HHandle, dlpruning_handle: HHandle ) -> HHandle

Herror T_gen_dl_pruned_model( const Htuple DLModelHandleToPrune, const Htuple DLPruningHandle, Htuple* DLModelHandlePruned )

HDlModel HDlModel::GenDlPrunedModel( const HDlPrune& DLPruningHandle ) const

HDlModel HDlModel.GenDlPrunedModel( HDlPrune DLPruningHandle )

Description

The operator gen_dl_pruned_modelGenDlPrunedModel copies the input model DLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune and returns the pruned copy in DLModelHandlePrunedDLModelHandlePruneddlmodel_handle_pruned. Note that gen_dl_pruned_modelGenDlPrunedModel supports only deep learning models of 'type'"type"='classification'"classification".

The parameter DLPruningHandleDLPruningHandledlpruning_handle provides the necessary information as e.g., the selected pruning mode, the percentage or the kernel scores. See create_dl_pruningCreateDlPruning for further information about implemented pruning modes.

Behavior in special cases:

• In case the set amount of pruning 'percentage'"percentage" is too small to result in any removals, the returned model DLModelHandlePrunedDLModelHandlePruneddlmodel_handle_pruned is simply a copy of the input model DLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune.

• In case the model could not be pruned successfully, an empty handle is returned.

Execution information

Execution information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).

• Multithreading scope: global (may be called from any thread).

• Processed without parallelization.

Parameters

DLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune (input_control) dl_model → (handle)HTuple (HHandle)HDlModel, HTuple (IntPtr)HHandleHtuple (handle)

Input model.

DLPruningHandleDLPruningHandledlpruning_handle (input_control) dl_pruning → (handle)HTuple (HHandle)HDlPrune, HTuple (IntPtr)HHandleHtuple (handle)

Pruning data handle.

DLModelHandlePrunedDLModelHandlePruneddlmodel_handle_pruned (output_control) dl_model → (handle)HTuple (HHandle)HDlModel, HTuple (IntPtr)HHandleHtuple (handle)

Pruned model.

Combinations with other operators

Combinations

Possible predecessors

add_dl_pruning_batchAddDlPruningBatch, set_dl_pruning_paramSetDlPruningParam

Module

Deep Learning Professional